Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/m98/fluent/fluent-setupnpx skills add m98/fluent --skill fluent-setupgit clone --depth 1 https://github.com/m98/fluentWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00078 | $0.02293 |
| Opus 5 | $0.00039 | $0.01146 |
| Sonnet 5 | $0.00016 | $0.00459 |
| Haiku 4.5 | $0.00008 | $0.00229 |
Grade A, and why
fluent-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language Learning Setup
Overview
One-time onboarding that seeds all 6 databases in the Fluent data directory. After setup, every other skill reads from those files — this is the bootstrap. Also handles profile updates and progress resets for returning users.
The data directory is resolved at runtime (not hardcoded to ./data/):
$FLUENT_DATA_DIRif set$CLAUDE_PROJECT_DIR/data/if that path containslearner-profile.json(clone mode)./data/if./data/learner-profile.jsonexists (clone mode, cwd inside repo)~/.claude/fluent-data/otherwise (plugin-install default)
Always resolve it via the helper rather than writing literal data/ paths:
FLUENT_DATA="$(python3 "${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks/ensure_data_dir.py")"
or from Python:
import sys
sys.path.insert(0, f"{PLUGIN_ROOT}/.claude/hooks")
from fluent_paths import ensure_data_dir
DATA = ensure_data_dir()
When to Use
Trigger this skill only when the learner types /fluent-setup. The skill is gated with disable-model-invocation: true — re-running can reset a learner's progress, so it must never auto-fire from an ambiguous prompt.
Skip this skill if a profile already exists and the learner did not ask to change anything; route them to /fluent-learn or /fluent-progress instead.
Instructions
1. Check for existing profile
Resolve the data directory first, then probe for learner-profile.json:
DATA_DIR="$(python3 -c "
import sys; sys.path.insert(0, '${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks')
from fluent_paths import data_dir
print(data_dir())
")"
test -f "$DATA_DIR/learner-profile.json" && echo "exists" || echo "new"
If it exists, jump to Profile updates below. Otherwise continue.
2. Welcome
# 🌍 Welcome to Your Personal Language Learning System!
This AI-powered system will help you learn any language through:
- 📊 Systematic progress tracking
- 🧠 Spaced repetition (scientifically proven)
- 🎮 Gamification (streaks, achievements)
- 📈 Adaptive difficulty
- 🎯 Personalized to YOUR goals
**Let's get you set up!** (~5 minutes)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 251 lines · 78 tokens per session scan A 35895b5b3e4a
fluent-setup is a skill published in the GitHub repository m98/fluent (381 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 2,293 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…